Video Friday this is your weekly selection of amazing robotics videos collected by your friends on IEEE spectrum robotics. We're also posting a weekly calendar of upcoming robotics events for the next few months. Please send us your events to turn on.
IKRA 2026: 1–5 June 2026, VIENNA
Enjoy today's videos!
EPFL Scientists have integrated discarded crustacean shells into robotic devices, harnessing the strength and flexibility of natural materials for robotic applications.
[ EPFL ]
Finally a good one humanoid robot demo!
Although I never trust demo videos where everything works very well once, and then very well every time.
[ LimX Dynamics ]
Thank you, Jinyan!
I understand how these structures work, I really do. But watching something solid get squeezed out of a flexible spool always feels a little magical.
[ AAAS ]
Thank you, Kyujin!
I'm not sure what “industrial grade” actually means, but I want “automotive grade” robots where they can easily run for six months to a year without any maintenance.
[ Pudu Robotics ]
Thanks Mandy!
When you begin to suspect that your robotic charging of electric vehicles The solution costs more than your car.
[ Flexiv ]
Yes, if the app for this humanoid actually created robot parts using a hammer and anvil, then I would be impressed.
[ EngineAI ]
Researchers at Columbia Engineering have developed a robot that can learn the human sense of neatness. The researchers trained the system by showing it millions of examples rather than teaching it specific instructions. The result is a model that can look at a cluttered countertop and organize scattered items into order.
[ Paper ]
Why haven't we seen this in humanoids? robotics video more?
[ HUCEBOT ]
While I definitely value field testing, it's also worth asking to what extent your robot actually faces challenges in your chosen field conditions.
[ DEEP Robotics ]
Introducing the HMND 01 Alpha Bipedal – autonomous, adaptive, built to perform in real-world conditions. Built in 5 months, runs stable after 48 hours of training.
[ Humanoid ]
Unitry says that “this is necessary to check the overall reliability of the robot”, but I really wonder how useful such a reliability check actually is.
[ Unitree ]
The GRASP Robotics Workshop at the University of Pennsylvania was led by Jie Tang from Google DeepMindon the topic “Gemini Robotics: Introducing Artificial Intelligence into the Physical World.”
Recent advances in large-scale multimodal models have led to remarkable universal capabilities in digital domains, but translating them to physical agents such as robots remains a major challenge. In this talk, I will present Gemini Robotics, an advanced universal Vision-Language-Action (VLA) model capable of directly controlling robots. Additionally, I will discuss the challenges, learnings, and future research directions in robotics. foundation models.
[ University of Pennsylvania GRASP Laboratory ]
Articles from your site
Related articles on the Internet
